DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Myeong Hyeon | ko |
dc.contributor.author | Kim, Dongjae | ko |
dc.contributor.author | Jo, Eunsong | ko |
dc.contributor.author | Lee, Sang Wan | ko |
dc.date.accessioned | 2022-09-01T10:00:34Z | - |
dc.date.available | 2022-09-01T10:00:34Z | - |
dc.date.created | 2022-09-01 | - |
dc.date.created | 2022-09-01 | - |
dc.date.issued | 2022-02 | - |
dc.identifier.citation | 10th International Winter Conference on Brain-Computer Interface (BCI) | - |
dc.identifier.issn | 2572-7672 | - |
dc.identifier.uri | http://hdl.handle.net/10203/298249 | - |
dc.description.abstract | Recent studies have found that human strategic decision-making is well explained by a mixture of model-based (MB) and model-free reinforcement learning (MF) [1], and the information necessary for this combination can be decoded from EEG signals [2]. These findings raise the expectation that BCI systems can be built to accommodate high-level cognitive processes, such as strategic decision making, planning, and goal-directed learning. However, these demonstrations were confined to simple Markov decision tasks, significantly undermining its applicability. While open-source benchmarks provide various realistic scenarios, most of them do not require model-based learning. To settle this issue, we present a novel task paradigm enabling the test of goal-driven learning and strategic decision-making in a realistic environment. Our task is implemented based on the open AI-based Atari game environment. We manipulated three task variables previously known to induce goal-driven learning: goal condition, state transition uncertainty, and task complexity. Lastly, we discuss potential applications in cognitive science, machine learning, and BCI. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Goal-Driven Atari Environment | - |
dc.type | Conference | - |
dc.identifier.wosid | 000814683300045 | - |
dc.identifier.scopusid | 2-s2.0-85146199233 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 10th International Winter Conference on Brain-Computer Interface (BCI) | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | High1 Resort | - |
dc.identifier.doi | 10.1109/BCI53720.2022.9735085 | - |
dc.contributor.localauthor | Lee, Sang Wan | - |
dc.contributor.nonIdAuthor | Kim, Myeong Hyeon | - |
dc.contributor.nonIdAuthor | Kim, Dongjae | - |
dc.contributor.nonIdAuthor | Jo, Eunsong | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.